From: Oleg Nesterov <oleg@tv-sign.ru>

With or without this patch, multi-threaded init's are not fully supported,
but do_exit() is completely wrong.  This becomes a real problem when we
support pid namespaces.

1. do_exit() panics when the main thread of /sbin/init exits. It should not
   until the whole thread group exits. Move the code below, under the
   "if (group_dead)" check.

   Note: this means that forget_original_parent() can use an already dead
   child_reaper()'s task_struct. This is OK for /sbin/init because

   	- do_wait() from alive sub-thread still can reap a zombie, we iterate
   	  over all sub-thread's ->children lists

   	- do_notify_parent() will wakeup some alive sub-thread because it sends
   	  the group-wide signal

   However, we should remove choose_new_parent()->BUG_ON(reaper->exit_state)
   for this.

2. We are playing games with ->nsproxy->pid_ns. This code is bogus today, and
   it has to be changed anyway when we really support pid namespaces, just
   remove it.

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Roland McGrath <roland@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 kernel/exit.c |   31 +++++++++++--------------------
 1 file changed, 11 insertions(+), 20 deletions(-)

diff -puN kernel/exit.c~handle-the-multi-threaded-inits-exit-properly kernel/exit.c
--- a/kernel/exit.c~handle-the-multi-threaded-inits-exit-properly
+++ a/kernel/exit.c
@@ -591,17 +591,6 @@ static void exit_mm(struct task_struct *
 	mmput(mm);
 }
 
-static inline void
-choose_new_parent(struct task_struct *p, struct task_struct *reaper)
-{
-	/*
-	 * Make sure we're not reparenting to ourselves and that
-	 * the parent is not a zombie.
-	 */
-	BUG_ON(p == reaper || reaper->exit_state);
-	p->real_parent = reaper;
-}
-
 static void
 reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
 {
@@ -709,7 +698,7 @@ forget_original_parent(struct task_struc
 
 		if (father == p->real_parent) {
 			/* reparent with a reaper, real father it's us */
-			choose_new_parent(p, reaper);
+			p->real_parent = reaper;
 			reparent_thread(p, father, 0);
 		} else {
 			/* reparent ptraced task to its real parent */
@@ -730,7 +719,7 @@ forget_original_parent(struct task_struc
 	}
 	list_for_each_safe(_p, _n, &father->ptrace_children) {
 		p = list_entry(_p, struct task_struct, ptrace_list);
-		choose_new_parent(p, reaper);
+		p->real_parent = reaper;
 		reparent_thread(p, father, 1);
 	}
 }
@@ -881,6 +870,14 @@ static void check_stack_usage(void)
 static inline void check_stack_usage(void) {}
 #endif
 
+static inline void exit_child_reaper(struct task_struct *tsk)
+{
+	if (likely(tsk->group_leader != child_reaper(tsk)))
+		return;
+
+	panic("Attempted to kill init!");
+}
+
 fastcall NORET_TYPE void do_exit(long code)
 {
 	struct task_struct *tsk = current;
@@ -894,13 +891,6 @@ fastcall NORET_TYPE void do_exit(long co
 		panic("Aiee, killing interrupt handler!");
 	if (unlikely(!tsk->pid))
 		panic("Attempted to kill the idle task!");
-	if (unlikely(tsk == child_reaper(tsk))) {
-		if (tsk->nsproxy->pid_ns != &init_pid_ns)
-			tsk->nsproxy->pid_ns->child_reaper = init_pid_ns.child_reaper;
-		else
-			panic("Attempted to kill init!");
-	}
-
 
 	if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
 		current->ptrace_message = code;
@@ -950,6 +940,7 @@ fastcall NORET_TYPE void do_exit(long co
 	}
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
+		exit_child_reaper(tsk);
 		hrtimer_cancel(&tsk->signal->real_timer);
 		exit_itimers(tsk->signal);
 	}
_